From: Saul Wold Date: Tue, 8 Feb 2022 15:02:11 +0000 (-0800) Subject: create-spdx: Get SPDX-License-Identifier from source X-Git-Url: https://code.ossystems.io/gitweb?a=commitdiff_plain;h=51e5f328635eb022143178c3169bae719509697a;p=openembedded-core.git create-spdx: Get SPDX-License-Identifier from source This patch will read the begining of source files and try to find the SPDX-License-Identifier to populate the licenseInfoInFiles field for each source file. This does not populate licenseConcluded at this time, nor rolls it up to package level. We read as binary file since some source code seem to have some binary characters, the license is then converted to ascii strings. Signed-off-by: Saul Wold Signed-off-by: Richard Purdie --- diff --git a/meta/classes/create-spdx.bbclass b/meta/classes/create-spdx.bbclass index 8b4203fdb5..64aada8593 100644 --- a/meta/classes/create-spdx.bbclass +++ b/meta/classes/create-spdx.bbclass @@ -37,6 +37,23 @@ SPDX_SUPPLIER[doc] = "The SPDX PackageSupplier field for SPDX packages created f do_image_complete[depends] = "virtual/kernel:do_create_spdx" +def extract_licenses(filename): + import re + + lic_regex = re.compile(b'^\W*SPDX-License-Identifier:\s*([ \w\d.()+-]+?)(?:\s+\W*)?$', re.MULTILINE) + + try: + with open(filename, 'rb') as f: + size = min(15000, os.stat(filename).st_size) + txt = f.read(size) + licenses = re.findall(lic_regex, txt) + if licenses: + ascii_licenses = [lic.decode('ascii') for lic in licenses] + return ascii_licenses + except Exception as e: + bb.warn(f"Exception reading {filename}: {e}") + return None + def get_doc_namespace(d, doc): import uuid namespace_uuid = uuid.uuid5(uuid.NAMESPACE_DNS, d.getVar("SPDX_UUID_NAMESPACE")) @@ -232,6 +249,11 @@ def add_package_files(d, doc, spdx_pkg, topdir, get_spdxid, get_types, *, archiv checksumValue=bb.utils.sha256_file(filepath), )) + if "SOURCE" in spdx_file.fileTypes: + extracted_lics = extract_licenses(filepath) + if extracted_lics: + spdx_file.licenseInfoInFiles = extracted_lics + doc.files.append(spdx_file) doc.add_relationship(spdx_pkg, "CONTAINS", spdx_file) spdx_pkg.hasFiles.append(spdx_file.SPDXID)